Delgado Miguel, Cuéllar Manuel P, Pegalajar Maria Carmen
Department of Computer Science and Artificial Intelligence, University of Grenada, Grenada, Spain.
IEEE Trans Syst Man Cybern B Cybern. 2008 Apr;38(2):381-403. doi: 10.1109/TSMCB.2007.912937.
The application of neural networks to solve a problem involves tasks with a high computational cost until a suitable network is found, and these tasks mainly involve the selection of the network topology and the training step. We usually select the network structure by means of a trial-and-error procedure, and we then train the network. In the case of recurrent neural networks (RNNs), the lack of suitable training algorithms sometimes hampers these procedures due to vanishing gradient problems. This paper addresses the simultaneous training and topology optimization of RNNs using multiobjective hybrid procedures. The proposal is based on the SPEA2 and NSGA2 algorithms for making hybrid methods using the Baldwinian hybridization strategy. We also study the effects of the selection of the objectives, crossover, and mutation in the diversity during evolution. The proposals are tested in the experimental section to train and optimize the networks in the competition on artificial time-series (CATS) benchmark.
将神经网络应用于解决问题涉及到计算成本很高的任务，直到找到合适的网络为止，而这些任务主要涉及网络拓扑的选择和训练步骤。我们通常通过反复试验的过程来选择网络结构，然后对网络进行训练。在循环神经网络（RNN）的情况下，由于梯度消失问题，缺乏合适的训练算法有时会阻碍这些过程。本文采用多目标混合方法解决RNN的同步训练和拓扑优化问题。该提议基于SPEA2和NSGA2算法，使用鲍德温杂交策略来构建混合方法。我们还研究了目标选择、交叉和变异对进化过程中多样性的影响。在实验部分对这些提议进行了测试，以在人工时间序列（CATS）基准竞赛中训练和优化网络。
